Model averaging based on the least squares estimator or the maximum likelihood estimator has been widely followed, while model averaging based on the generalized method of moments is almost rarely addressed. This paper is concerned with a model averaging method based on the weighted generalized method of moments for missing responses problem. The weight vector for model averaging is obtained via minimizing the leave-one-out cross validation criterion. With some mild conditions, the asymptotic optimality of the proposed method in the sense that it can achieve the lowest squared error asymptotically is proved. Some numerical experiments are conducted to evaluate the proposed method with the existing related ones, and the results suggest that the proposed method performs relatively well.
Citation: Zhongqi Liang, Yanqiu Zhou. Model averaging based on weighted generalized method of moments with missing responses[J]. AIMS Mathematics, 2023, 8(9): 21683-21699. doi: 10.3934/math.20231106
Model averaging based on the least squares estimator or the maximum likelihood estimator has been widely followed, while model averaging based on the generalized method of moments is almost rarely addressed. This paper is concerned with a model averaging method based on the weighted generalized method of moments for missing responses problem. The weight vector for model averaging is obtained via minimizing the leave-one-out cross validation criterion. With some mild conditions, the asymptotic optimality of the proposed method in the sense that it can achieve the lowest squared error asymptotically is proved. Some numerical experiments are conducted to evaluate the proposed method with the existing related ones, and the results suggest that the proposed method performs relatively well.
[1] | T. Ando, K. C. Li, A model-averaging approach for high-dimensional regression, J. Am. Stat. Assoc., 109 (2014), 254–265. https://doi.org/10.1080/01621459.2013.838168 doi: 10.1080/01621459.2013.838168 |
[2] | T. Ando, K. C. Li, A weight-relaxed model averaging approach for high-dimensional generalized linear models, Ann. Stat., 45 (2017), 2654–2679. https://doi.org/10.1214/17-aos1538 doi: 10.1214/17-aos1538 |
[3] | F. J. DiTraglia, J. Francis, Using invalid instruments on purpose: Focused moment selection and averaging for GMM, J. Econ., 195 (2016), 187–208. https://doi.org/10.1016/j.jeconom.2016.07.006 doi: 10.1016/j.jeconom.2016.07.006 |
[4] | B. E. Hansen, Least squares model averaging, Econometrica, 75 (2007), 1175–1189. https://doi.org/10.1111/j.1468-0262.2007.00785.x doi: 10.1111/j.1468-0262.2007.00785.x |
[5] | B. E. Hansen, J. S. Racine, Jackknife model averaging, J. Econ., 167 (2012), 38–46. https://doi.org/10.1111/j.1747-4477.2012.00344.x |
[6] | L. P. Hansen, Large sample properties of generalized method of moments estimators, Econometrica, 50 (1982), 1029–1054. https://doi.org/10.2307/1912775 doi: 10.2307/1912775 |
[7] | N. Hens, M. Aerts, G. Molenberghs, Model selection for incomplete and design-based samples, Stat. Med., 25 (2006), 2502–2520. https://doi.org/10.1002/sim.2559 doi: 10.1002/sim.2559 |
[8] | K. C. Li, Asymptotic optimality for $C_p, C_L$, cross-validation and generalized cross-validation: Discrete index set, Ann. Stat., 15 (1987), 958–975. https://doi.org/10.1214/aos/1176350486 doi: 10.1214/aos/1176350486 |
[9] | J. Liao, G. Zou, Corrected mallows citerion for model averaging, Comput. Stat. Data Anal., 144 (2020), 106902. https://doi.org/10.1016/j.csda.2019.106902 doi: 10.1016/j.csda.2019.106902 |
[10] | R. J. A. Little, D. B. Rubin, Statistical analysis with missing data (2Eds.), 2002, Hoboken, NJ: Wiley. https://doi.org/10.1002/9781119013563 |
[11] | Q. Liu, R. Okui, Heteroscedasticity-robust $C_p$ model averaging, Econ. J., 16 (2013), 463–472. https://doi.org/10.1111/ectj.12009 doi: 10.1111/ectj.12009 |
[12] | Q. Liu, R. Okui, A. Yoshimura, Generalized least squares model averaging, Econ. Rev., 35 (2016), 1692–1752. https://doi.org/10.1080/07474938.2015.1092817 doi: 10.1080/07474938.2015.1092817 |
[13] | N. T. Longford, Model Selection and efficiency: is 'which model...?' the right question? J. R. Stat. Soc. A Stat., 168 (2005), 469–472. https://doi.org/10.1111/j.1467-985x.2005.00366.x |
[14] | R. Luo, Q. Wang, Empirical likelihood based weighted GMM estimation with missing response at random, J. Stat. Plan. Infer., 156 (2015), 64–79. https://doi.org/10.1016/j.jspi.2014.07.011 doi: 10.1016/j.jspi.2014.07.011 |
[15] | A. Raftery, Y. Zheng, Discussion: Performance of bayesian model averaging, J. Am. Stat. Assoc., 98 (2003), 931–938. https://doi.org/10.1198/016214503000000891 doi: 10.1198/016214503000000891 |
[16] | Z. Sun, Z. Su, J. Ma, Focused vector information criterion model selection and model averaging regression with missing response, Metrika, 77 (2014), 415–432. https://doi.org/10.1007/s00184-013-0446-8 doi: 10.1007/s00184-013-0446-8 |
[17] | A. T. K. Wan, X. Zhang, G. Zou, Least squares model averaging by mallows criterion, J. Econ., 156 (2010), 277–283. https://doi.org/10.1016/j.jeconom.2009.10.030 doi: 10.1016/j.jeconom.2009.10.030 |
[18] | Q. Wang, J. N. K. Rao, Empirical likelihood-based inference under imputation for missing response data, Ann. Stat., 30 (2002), 896–924. https://doi.org/10.1214/aos/1028674845 doi: 10.1214/aos/1028674845 |
[19] | Q. Wang, Z. Sun, Estimation in partially linear models with missing responses at random, J. Multivariate Anal., 98 (2007), 1470–1493. https://doi.org/10.1016/j.jmva.2006.10.003 doi: 10.1016/j.jmva.2006.10.003 |
[20] | W. Wang, Q. Zhang, X. Zhang, X. Li, Model averaging based on generalized method of moments, Econ. Lett., 200 (2021), 109735. https://doi.org/10.1016/j.econlet.2021.109735 doi: 10.1016/j.econlet.2021.109735 |
[21] | Y. Wei, Q. Wang, Cross-validation-based model averaging in linear models with response missing at random, Stat. Prob. Lett., 171 (2021), 108990. https://doi.org/10.1016/j.spl.2020.108990 doi: 10.1016/j.spl.2020.108990 |
[22] | J. Xie, X. Yan, N. Tang, A model averaging method for high-dimensional regression with missing responses at random, Stat. Sinica, 31 (2021), 1005–1026. https://doi.org/10.5705/ss.202018.0297 doi: 10.5705/ss.202018.0297 |
[23] | X. Zhang, Model averaging by least squares approximation, Sci. Sinica Math., 51 (2021), 535–548. https://doi.org/10.1360/n012019-00137 doi: 10.1360/n012019-00137 |
[24] | X. Zhang, Optimal model averaging based on generalized method of moments, Stat. Sinica, 31 (2021), 2103–2122. https://doi.org/10.5705/ss.202019.0230 doi: 10.5705/ss.202019.0230 |
[25] | X. Zhang, H. Liang, Focused information criterion and model averaging for generalized additive partial linear models, Ann. Stat., 39 (2011), 174–200. https://doi.org/10.1214/10-aos832 doi: 10.1214/10-aos832 |
[26] | X. Zhang, W. Wang, Optimal model averaging estimation for partially linear models, Stat. Sinica, 29 (2019), 693–718. https://doi.org/10.5705/ss.202015.0392 doi: 10.5705/ss.202015.0392 |
[27] | X. Zhang, D. Yu, G. Zou, H. Liang, Optimal model averaging estimation for generalized linear models and generalized linear mixed-effects models, J. Am. Stat. Assoc., 111 (2016), 1775–1790. https://doi.org/10.1080/01621459.2015.1115762 doi: 10.1080/01621459.2015.1115762 |
[28] | R. Zhu, A. T. K. Wan, X. Zhang, G. Zou, A mallows-type model averaging estimator for the varying-coefficient partially linear model, J. Am. Stat. Assoc., 114 (2019), 882–892. https://doi.org/10.1080/01621459.2018.1456936 doi: 10.1080/01621459.2018.1456936 |